Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1008 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9328. Min Act: -0.0000

Data Index: 1417558 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 3.0674. Min Range: -3.0674

Max Act: 3.0674. Min Act: -0.0000

Data Index: 1545614 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 3.0674. Min Range: -3.0674

Max Act: 3.0453. Min Act: -0.0000

Data Index: 1518220 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.7890. Min Act: -0.0000

Data Index: 1484322 (Python Code)

Max Activating Token Index: 682

Text #4

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.6391. Min Act: -0.0000

Data Index: 1457174 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.7890. Min Act: -0.0000

Data Index: 1468620 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.3812. Min Act: -0.0000

Data Index: 1446048 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.2667. Min Act: -0.0000

Data Index: 1519960 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.0964. Min Act: -0.0000

Data Index: 1564504 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.2602. Min Act: -0.0000

Data Index: 1468845 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1373292 (Python Code)

Max Activating Token Index: 752

Text #11

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.2127. Min Act: -0.0000

Data Index: 1617965 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.0802. Min Act: -0.0000

Data Index: 1579029 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.0776. Min Act: -0.0000

Data Index: 1453809 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1586946 (Python Code)

Max Activating Token Index: 715

Text #15

Max Range: 3.0674. Min Range: -3.0674

Max Act: 1.9471. Min Act: -0.0000

Data Index: 1576528 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1546692 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 3.0674. Min Range: -3.0674

Max Act: 1.8799. Min Act: -0.0000

Data Index: 1644883 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 3.0674. Min Range: -3.0674

Max Act: 1.8187. Min Act: -0.0000

Data Index: 1459942 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 3.0674. Min Range: -3.0674

Max Act: 1.9712. Min Act: -0.0000

Data Index: 1370573 (Python Code)

Max Activating Token Index: 302